CLAIFeb 21, 2025

Sparsity May Be All You Need: Sparse Random Parameter Adaptation

IBM
arXiv:2502.15975v35 citationsh-index: 33EMNLP
Originality Incremental advance
AI Analysis

This addresses the problem of computational and memory inefficiency in fine-tuning for AI practitioners, though it is incremental as it builds on existing PEFT methods.

The paper tackles the high cost of fine-tuning large language models by proposing a sparse random parameter adaptation method that trains only a small, randomly selected subset of parameters, finding it competitive with LoRA when using a similar number of trainable parameters.

Full fine-tuning of large language models for alignment and task adaptation has become prohibitively expensive as models have grown in size. Parameter-Efficient Fine-Tuning (PEFT) methods aim at significantly reducing the computational and memory resources needed for fine-tuning these models by only training on a small number of parameters instead of all model parameters. Currently, the most popular PEFT method is the Low-Rank Adaptation (LoRA), which freezes the parameters of the model and introduces a small set of trainable parameters in the form of low-rank matrices. We propose simply reducing the number of trainable parameters by randomly selecting a small proportion of the model parameters to train on, while fixing all other parameters, without any additional prior assumptions such as low-rank structures. In this paper, we compare the efficiency and performance of our proposed approach to other PEFT methods as well as full parameter fine-tuning. We find our method to be competitive with LoRA when using a similar number of trainable parameters. Our findings suggest that what truly matters for a PEFT technique to perform well is not necessarily the specific adapter structure, but rather the number of trainable parameters being used.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes